Conducting data analysis tasks rarely occur in isolation. Especially in intelligence analysis scenarios where different experts contribute knowledge to a shared understanding, members must communicate how insights develop to establish common ground among collaborators. The use of provenance to communicate analytic sensemaking carries promise by describing the interactions and summarizing the steps taken to reach insights. Yet, no universal guidelines exist for communicating provenance in different settings. Our work focuses on the presentation of provenance information and the resulting conclusions reached and strategies used by new analysts. In an open-ended, 30-minute, textual exploration scenario, we qualitatively compare how adding different types of provenance information (specifically data coverage and interaction history) affects analysts' confidence in conclusions developed, propensity to repeat work, filtering of data, identification of relevant information, and typical investigation strategies. We see that data coverage (i.e., what was interacted with) provides provenance information without limiting individual investigation freedom. On the other hand, while interaction history (i.e., when something was interacted with) does not significantly encourage more mimicry, it does take more time to comfortably understand, as represented by less confident conclusions and less relevant information-gathering behaviors. Our results contribute empirical data towards understanding how provenance summarizations can influence analysis behaviors.

While EXplainable Artificial Intelligence (XAI) approaches aim to improve human-AI collaborative decision-making by improving model transparency and mental model formations, experiential factors associated with human users can cause challenges in ways system designers do not anticipate. In this article, we first showcase a user study on how anchoring bias can potentially affect mental model formations when users initially interact with an intelligent system and the role of explanations in addressing this bias. Using a video activity recognition tool in cooking domain, we asked participants to verify whether a set of kitchen policies are being followed, with each policy focusing on a weakness or a strength. We controlled the order of the policies and the presence of explanations to test our hypotheses. Our main finding shows that those who observed system strengths early on were more prone to automation bias and made significantly more errors due to positive first impressions of the system, while they built a more accurate mental model of the system competencies. However, those who encountered weaknesses earlier made significantly fewer errors, since they tended to rely more on themselves, while they also underestimated model competencies due to having a more negative first impression of the model. Motivated by these findings and similar existing work, we formalize and present a conceptual model of user’s past experiences that examine the relations between user’s backgrounds, experiences, and human factors in XAI systems based on usage time. Our work presents strong findings and implications, aiming to raise the awareness of AI designers toward biases associated with user impressions and backgrounds.

Research in interpretable machine learning proposes different computational and human subject approaches to evaluate model saliency explanations. These approaches measure different qualities of explanations to achieve diverse goals in designing interpretable machine learning systems. In this paper, we propose a benchmark for image and text domains using multi-layer human attention masks aggregated from multiple human annotators. We then present an evaluation study to compare model saliency explanations obtained using Grad-cam and LIME techniques to human understanding and acceptance. We demonstrate our benchmark’s utility for quantitative evaluation of model explanations by comparing it with human subjective ratings and ground-truth single-layer segmentation masks evaluations. Our study results show that our threshold agnostic evaluation method with the human attention baseline is more effective than single-layer object segmentation masks to ground truth. Our experiments also reveal user biases in the subjective rating of model saliency explanations.

EXplainable Artificial Intelligence (XAI) approaches are used to bring transparency to machine learning and artificial intelligence models, and hence, improve the decision-making process for their end-users. While these methods aim to improve human understanding and their mental models, cognitive biases can still influence a user’s mental model and decision-making in ways that system designers do not anticipate. This paper presents research on cognitive biases due to ordering effects in intelligent systems. We conducted a controlled user study to understand how the order of observing system weaknesses and strengths can affect the user’s mental model, task performance, and reliance on the intelligent system, and we investigate the role of explanations in addressing this bias. Using an explainable video activity recognition tool in the cooking domain, we asked participants to verify whether a set of kitchen policies are being followed, with each policy focusing on a weakness or a strength. We controlled the order of the policies and the presence of explanations to test our hypotheses. Our main finding shows that those who observed system strengths early-on were more prone to automation bias and made significantly more errors due to positive first impressions of the system, while they built a more accurate mental model of the system competencies. On the other hand, those who encountered weaknesses earlier made significantly fewer errors since they tended to rely more on themselves, while they also underestimated model competencies due to having a more negative first impression of the model. Our work presents strong findings that aim to make intelligent system designers aware of such biases when designing such tools.

Students' interest in game development often leads departments to attempt to put together a stand-alone game development course. We have used both Unity and Unreal for just such a course. Unity and Unreal are discussed here in the context of how viable they are and how they compare in terms of usefulness for teaching game development. We also present them in context of high level overviews of other game engines and discuss which factors add to a more effective game engine for teaching game development. This paper is intended to help answer some of the questions asked by those without experience in the field who find themselves developing stand-alone game development courses.